Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1526 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1332864 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.8760. Min Act: -0.0000

Data Index: 210056 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.8010. Min Act: -0.0000

Data Index: 221257 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1629113 (Python Code)

Max Activating Token Index: 877

Text #4

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7495. Min Act: -0.0000

Data Index: 969522 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1649580 (Python Code)

Max Activating Token Index: 437

Text #6

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1607477 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1412421 (Python Code)

Max Activating Token Index: 947

Text #8

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1492706 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1426147 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1400791 (Python Code)

Max Activating Token Index: 591

Text #11

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1575424 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7488. Min Act: -0.0000

Data Index: 1413799 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1643462 (Python Code)

Max Activating Token Index: 827

Text #14

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7285. Min Act: -0.0000

Data Index: 747878 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1463301 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1535018 (Python Code)

Max Activating Token Index: 770

Text #17

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1634909 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1392575 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.9757. Min Range: -0.9757

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1586341 (Python Code)

Max Activating Token Index: 627